Voice Activity Detection Based on High Order Statistics and Online EM Algorithm


IEICE TRANSACTIONS on Information and Systems   Vol.E91-D    No.12    pp.2854-2861
Publication Date: 2008/12/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e91-d.12.2854
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Speech and Hearing
speech recognition,  voice activity detection,  high order statistics,  online EM,  

Full Text: PDF(1008KB)>>
Buy this Article

A new online, unsupervised voice activity detection (VAD) method is proposed. The method is based on a feature derived from high-order statistics (HOS), enhanced by a second metric based on normalized autocorrelation peaks to improve its robustness to non-Gaussian noises. This feature is also oriented for discriminating between close-talk and far-field speech, thus providing a VAD method in the context of human-to-human interaction independent of the energy level. The classification is done by an online variation of the Expectation-Maximization (EM) algorithm, to track and adapt to noise variations in the speech signal. Performance of the proposed method is evaluated on an in-house data and on CENSREC-1-C, a publicly available database used for VAD in the context of automatic speech recognition (ASR). On both test sets, the proposed method outperforms a simple energy-based algorithm and is shown to be more robust against the change in speech sparsity, SNR variability and the noise type.

open access publishing via